bpf: Initialize same number of free nodes for each pcpu_freelist

[ Upstream commit 4b45cd81f737d79d0fbfc0d320a1e518e7f0bbf0 ]

pcpu_freelist_populate() initializes nr_elems / num_possible_cpus() + 1
free nodes for some CPUs, and then possibly one CPU with fewer nodes,
followed by remaining cpus with 0 nodes. For example, when nr_elems == 256
and num_possible_cpus() == 32, CPU 0~27 each gets 9 free nodes, CPU 28 gets
4 free nodes, CPU 29~31 get 0 free nodes, while in fact each CPU should get
8 nodes equally.

This patch initializes nr_elems / num_possible_cpus() free nodes for each
CPU firstly, then allocates the remaining free nodes by one for each CPU
until no free nodes left.

Fixes: e19494edab82 ("bpf: introduce percpu_freelist")
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20221110122128.105214-1-xukuohai@huawei.com
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
index 3d897de8906121cfa95a1c34a0b8170f02fba4f8..bbab8bb4b2fdabde2725fa0676343a29255b9a79 100644 (file)
--- a/kernel/bpf/percpu_freelist.c
+++ b/kernel/bpf/percpu_freelist.c
@@ -102,22 +102,21 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
                            u32 nr_elems)
 {
        struct pcpu_freelist_head *head;
-       int i, cpu, pcpu_entries;
+       unsigned int cpu, cpu_idx, i, j, n, m;
 
-       pcpu_entries = nr_elems / num_possible_cpus() + 1;
-       i = 0;
+       n = nr_elems / num_possible_cpus();
+       m = nr_elems % num_possible_cpus();
 
+       cpu_idx = 0;
        for_each_possible_cpu(cpu) {
-again:
                head = per_cpu_ptr(s->freelist, cpu);
-               /* No locking required as this is not visible yet. */
-               pcpu_freelist_push_node(head, buf);
-               i++;
-               buf += elem_size;
-               if (i == nr_elems)
-                       break;
-               if (i % pcpu_entries)
-                       goto again;
+               j = n + (cpu_idx < m ? 1 : 0);
+               for (i = 0; i < j; i++) {
+                       /* No locking required as this is not visible yet. */
+                       pcpu_freelist_push_node(head, buf);
+                       buf += elem_size;
+               }
+               cpu_idx++;
        }
 }